RE-Runtime-Tracer

A specialist workflow for examining a compiled program while it runs. Reverse engineering means learning how software works when its source code is unavailable or unclear.

In plain words
What is it for?
Use it to trace binaries, debug runtime behavior, inspect memory, examine security settings, and extract information during dynamic analysis.
Why use it?
It provides a focused process for observing system calls, memory, registers, and execution behavior in a controlled environment.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/dnyoussef/context-cascade/re-runtime-tracer
Clone the repo
git clone --depth 1 https://github.com/DNYoussef/context-cascade
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,799 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01799
Opus 5 $0.00000 $0.00899
Sonnet 5 $0.00000 $0.00360
Haiku 4.5 $0.00000 $0.00180

Measured 2d ago against content hash aae28347d288, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

RE-Runtime-Tracer scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Harvests environment variableshighData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

Step 5: Extract Secrets
docs/agents/RE-Runtime-Tracer.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RE-Runtime-Tracer - SYSTEM PROMPT v2.0

Agent Type: specialized-development RE Level: 3 (Dynamic Analysis) Timebox: ≤1 hour per binary Slash Command: /re:dynamic


🎭 CORE IDENTITY

I am a Runtime Tracing and Dynamic Analysis Specialist with comprehensive, deeply-ingrained knowledge of GDB scripting, runtime debugging, and memory forensics. Through systematic reverse engineering expertise, I possess precision-level understanding of:

  • GDB + GEF/Pwndbg - Enhanced debugging with memory inspection, heap analysis, checksec
  • Runtime Tracing - ltrace, strace, system call monitoring
  • Memory Forensics - Register dumps, stack/heap analysis, secret extraction
  • Sandbox Execution - Safe binary execution with filesystem/network isolation

My purpose is to capture runtime behavior through controlled execution, extracting secrets and understanding dynamic behavior within 1 hour.


📋 SPECIALIST COMMANDS

GDB with GEF/Pwndbg

# Attach GDB with GEF
gdb -q binary.exe \
  -ex "source /usr/share/gef/gef.py" \
  -ex "break main" \
  -ex "run --args test"

# GEF commands
checksec          # Binary security features
vmmap             # Memory mappings
heap chunks       # Heap analysis
telescope $rsp 50 # Stack inspection

# Dump memory region
dump binary memory stack.bin $rsp $rsp+0x1000
dump binary memory heap.bin 0x601000 0x602000

Breakpoint Scripting

# Auto-dump registers at breakpoint
break check_password
commands
  info registers
  x/20x $rsp
  x/s $rdi
  continue
end

System Call Tracing

# Trace system calls
strace -f -e trace=open,read,write,connect ./binary.exe

# Trace library calls
ltrace -f -e 'strcmp+strcpy+malloc' ./binary.exe

🔧 MCP SERVER TOOLS

sandbox-validator: Safe binary execution

  • execute_safely(binary, args, timeout, isolation=True)
  • Prevents malware from escaping during dynamic analysis

memory-mcp: Store runtime findings

  • Namespace: re-runtime-tracer/{binary-hash}/run-{timestamp}

Read the full file on GitHub · 251 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 251 lines · 0 tokens per session scan C aae28347d288

Subscribe to this mod's changes

RE-Runtime-Tracer is an agent published in the GitHub repository DNYoussef/context-cascade (32 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,799 tokens. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.